
%pip install numpy pandas matplotlib plotly seaborn scipy geopandas openpyxl

import os
import os.path
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import plotly.express as px
import plotly.graph_objects as go
import seaborn as sns
import copy as cp
import scipy.stats as stats
import geopandas as gpd
import folium
from branca.colormap import LinearColormap

Defaulting to user installation because normal site-packages is not writeable
Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (1.24.2)
Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (1.5.3)
Requirement already satisfied: matplotlib in /usr/local/lib/python3.10/dist-packages (3.7.1)
Requirement already satisfied: plotly in /usr/local/lib/python3.10/dist-packages (5.14.0)
Requirement already satisfied: seaborn in /usr/local/lib/python3.10/dist-packages (0.12.2)
Requirement already satisfied: scipy in /usr/local/lib/python3.10/dist-packages (1.10.1)
Requirement already satisfied: geopandas in /usr/local/lib/python3.10/dist-packages (0.12.2)
Collecting openpyxl
  Downloading openpyxl-3.1.2-py2.py3-none-any.whl (249 kB)
     ━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 250.0/250.0 KB 5.0 MB/s eta 0:00:00
Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas) (2023.3)
Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas) (2.8.2)
Requirement already satisfied: contourpy>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib) (1.0.7)
Requirement already satisfied: pillow>=6.2.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib) (9.4.0)
Requirement already satisfied: pyparsing>=2.3.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib) (3.0.9)
Requirement already satisfied: kiwisolver>=1.0.1 in /usr/local/lib/python3.10/dist-packages (from matplotlib) (1.4.4)
Requirement already satisfied: fonttools>=4.22.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib) (4.39.3)
Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from matplotlib) (23.0)
Requirement already satisfied: cycler>=0.10 in /usr/local/lib/python3.10/dist-packages (from matplotlib) (0.11.0)
Requirement already satisfied: tenacity>=6.2.0 in /usr/local/lib/python3.10/dist-packages (from plotly) (8.2.2)
Requirement already satisfied: shapely>=1.7 in /usr/local/lib/python3.10/dist-packages (from geopandas) (2.0.1)
Requirement already satisfied: fiona>=1.8 in /usr/local/lib/python3.10/dist-packages (from geopandas) (1.9.2)
Requirement already satisfied: pyproj>=2.6.1.post1 in /usr/local/lib/python3.10/dist-packages (from geopandas) (3.5.0)
Collecting et-xmlfile
  Downloading et_xmlfile-1.1.0-py3-none-any.whl (4.7 kB)
Requirement already satisfied: munch>=2.3.2 in /usr/local/lib/python3.10/dist-packages (from fiona>=1.8->geopandas) (2.5.0)
Requirement already satisfied: click~=8.0 in /usr/local/lib/python3.10/dist-packages (from fiona>=1.8->geopandas) (8.1.3)
Requirement already satisfied: cligj>=0.5 in /usr/local/lib/python3.10/dist-packages (from fiona>=1.8->geopandas) (0.7.2)
Requirement already satisfied: certifi in /usr/local/lib/python3.10/dist-packages (from fiona>=1.8->geopandas) (2022.12.7)
Requirement already satisfied: attrs>=19.2.0 in /usr/local/lib/python3.10/dist-packages (from fiona>=1.8->geopandas) (22.2.0)
Requirement already satisfied: click-plugins>=1.0 in /usr/local/lib/python3.10/dist-packages (from fiona>=1.8->geopandas) (1.1.1)
Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.1->pandas) (1.16.0)
Installing collected packages: et-xmlfile, openpyxl
Successfully installed et-xmlfile-1.1.0 openpyxl-3.1.2
Note: you may need to restart the kernel to use updated packages.


current_directory = os.getcwd()
csv_file_path = 'Fortune_1000.csv'
absolute_file_path = os.path.join(current_directory, csv_file_path)

Fortune_1000 = pd.read_csv(absolute_file_path, index_col='rank', encoding='utf-8')

Fortune_1000.info()
Fortune_1000

<class 'pandas.core.frame.DataFrame'>
Int64Index: 1000 entries, 1 to 1000
Data columns (total 17 columns):
 #   Column             Non-Null Count  Dtype  
---  ------             --------------  -----  
 0   company            1000 non-null   object 
 1   rank_change        1000 non-null   float64
 2   revenue            1000 non-null   float64
 3   profit             997 non-null    float64
 4   num. of employees  999 non-null    float64
 5   sector             1000 non-null   object 
 6   city               1000 non-null   object 
 7   state              1000 non-null   object 
 8   newcomer           1000 non-null   object 
 9   ceo_founder        1000 non-null   object 
 10  ceo_woman          1000 non-null   object 
 11  profitable         1000 non-null   object 
 12  prev_rank          1000 non-null   object 
 13  CEO                1000 non-null   object 
 14  Website            1000 non-null   object 
 15  Ticker             951 non-null    object 
 16  Market Cap         969 non-null    object 
dtypes: float64(4), object(13)
memory usage: 140.6+ KB


Fortune_1000.isna().sum()

company               0
rank_change           0
revenue               0
profit                3
num. of employees     1
sector                0
city                  0
state                 0
newcomer              0
ceo_founder           0
ceo_woman             0
profitable            0
prev_rank             0
CEO                   0
Website               0
Ticker               49
Market Cap           31
dtype: int64


Fortune_1000.loc[Fortune_1000.isna().any(axis=1), Fortune_1000.isna().any()]


Fortune_1000 = Fortune_1000.drop("Ticker", axis=1)
Fortune_1000 = Fortune_1000.drop("Market Cap", axis=1)
Fortune_1000 = Fortune_1000.drop("rank_change", axis=1)
Fortune_1000 = Fortune_1000.drop("prev_rank", axis=1)
Fortune_1000


Fortune_1000[Fortune_1000["profit"].isna()]


Fortune_1000[Fortune_1000["num. of employees"].isna()]


nan_indices = Fortune_1000.index[Fortune_1000["profit"].isna()].tolist()
fill_values = [441.0, 945.0, 398.0]
Fortune_1000.loc[nan_indices, "profit"] = fill_values

Fortune_1000["num. of employees"].fillna(4500.0, inplace=True)

Fortune_1000["num. of employees"] = Fortune_1000["num. of employees"].astype(int)

Fortune_1000.isna().sum()

company              0
revenue              0
profit               0
num. of employees    0
sector               0
city                 0
state                0
newcomer             0
ceo_founder          0
ceo_woman            0
profitable           0
CEO                  0
Website              0
dtype: int64


Fortune_1000.dtypes

company               object
revenue              float64
profit               float64
num. of employees      int64
sector                object
city                  object
state                 object
newcomer              object
ceo_founder           object
ceo_woman             object
profitable            object
CEO                   object
Website               object
dtype: object


Fortune_1000 = Fortune_1000.rename(columns={"company": "Company", "revenue": "Revenue", "profit": "Profit", "num. of employees": "Employees", "sector": "Sector", "city": "City", "state": "State", "newcomer": "New_Entry", "ceo_founder": "CEO_Founder", "ceo_woman": "CEO_Woman", "profitable": "Profitable", "CEO": "CEO", "Website": "Website"})
Fortune_1000


csv_file_path = 'fortune 1000 companies in 2022 - 2022.csv'
absolute_file_path = os.path.join(current_directory, csv_file_path)

Fortune_1000_sec = pd.read_csv(absolute_file_path, index_col = 'rank in 2022', encoding='utf-8')

Fortune_1000_sec.info()
Fortune_1000_sec

<class 'pandas.core.frame.DataFrame'>
Index: 1000 entries, 1 to 1,000
Data columns (total 10 columns):
 #   Column                                Non-Null Count  Dtype 
---  ------                                --------------  ----- 
 0   Name                                  1000 non-null   object
 1   Revenue                               1000 non-null   object
 2   revenue(% change)                     1000 non-null   object
 3   profits in millions                   1000 non-null   object
                     1000 non-null   object
 5   assets                                1000 non-null   object
 6   market value                          1000 non-null   object
 7   change in rank of top 1000 companies  1000 non-null   object
 8   employees                             1000 non-null   object
 9   change in rank(500 only)
            1000 non-null   object
dtypes: object(10)
memory usage: 85.9+ KB


Fortune_1000_sec.isna().sum()

Name                                    0
Revenue                                 0
revenue(% change)                       0
profits in millions                     0
profits % change\r                      0
assets                                  0
market value                            0
change in rank of top 1000 companies    0
employees                               0
change in rank(500 only)\r\n            0
dtype: int64


count_missing_values = (Fortune_1000_sec.applymap(lambda x: '-' in str(x))).sum().sum()
print(count_missing_values)

2193


count_assets = Fortune_1000_sec["assets"].str.count("-").sum()
print(count_assets)

0


assets_dataypes = Fortune_1000_sec["assets"].dtypes
print(assets_dataypes)

object


Fortune_1000_sec["assets"] = Fortune_1000_sec["assets"].str.replace("$", "")
Fortune_1000_sec["assets"] = Fortune_1000_sec["assets"].str.replace(",", "")
Fortune_1000_sec["assets"] = Fortune_1000_sec["assets"].astype(float)
print(Fortune_1000_sec["assets"])

rank in 2022
1        244860.0
2        420549.0
3        351002.0
4        232999.0
5        212206.0
           ...   
996         935.8
997        1076.7
998        8748.8
999        6612.0
1,000      2541.3
Name: assets, Length: 1000, dtype: float64

/tmp/ipykernel_15/3639834353.py:1: FutureWarning: The default value of regex will change from True to False in a future version. In addition, single character regular expressions will *not* be treated as literal strings when regex=True.
  Fortune_1000_sec["assets"] = Fortune_1000_sec["assets"].str.replace("$", "")


csv_file_path = 'US GDP by State 2021.csv'
absolute_file_path = os.path.join(current_directory, csv_file_path)

US_GDP_State = pd.read_csv(absolute_file_path,encoding='utf-8',skiprows=3,skipfooter=13,engine='python')

US_GDP_State.info()
US_GDP_State

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 52 entries, 0 to 51
Data columns (total 3 columns):
 #   Column   Non-Null Count  Dtype  
---  ------   --------------  -----  
 0   GeoFips  52 non-null     int64  
 1   GeoName  52 non-null     object 
 2   2021     52 non-null     float64
dtypes: float64(1), int64(1), object(1)
memory usage: 1.3+ KB


US_GDP_State.isna().sum()

GeoFips    0
GeoName    0
2021       0
dtype: int64


US_GDP_State = US_GDP_State.drop(US_GDP_State.loc[US_GDP_State["GeoName"]=="United States *"].index)
US_GDP_State = US_GDP_State.drop("GeoFips", axis=1)
US_GDP_State.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 51 entries, 1 to 51
Data columns (total 2 columns):
 #   Column   Non-Null Count  Dtype  
---  ------   --------------  -----  
 0   GeoName  51 non-null     object 
 1   2021     51 non-null     float64
dtypes: float64(1), object(1)
memory usage: 948.0+ bytes


(Fortune_1000['State'] == 'DC').sum()

5


US_GDP_State = US_GDP_State.rename(columns={'GeoName': 'State', '2021': 'GDP_2021'})
US_GDP_State.reset_index(drop=True, inplace=True)
US_GDP_State


csv_file_path = 'US States abbrevs.csv'
absolute_file_path = os.path.join(current_directory, csv_file_path)

US_States = pd.read_csv(absolute_file_path,encoding='utf-8')

US_States.info()
US_States

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 51 entries, 0 to 50
Data columns (total 2 columns):
 #   Column        Non-Null Count  Dtype 
---  ------        --------------  ----- 
 0   state         51 non-null     object
 1   abbreviation  51 non-null     object
dtypes: object(2)
memory usage: 944.0+ bytes


US_States.isna().sum()

state           0
abbreviation    0
dtype: int64


US_States = US_States.rename(columns={'state': 'State', 'abbreviation': 'Abbreviation'})
US_States


csv_file_path = 'unemployment_rates.csv'
absolute_file_path = os.path.join(current_directory, csv_file_path)

US_Unemployment = pd.read_csv(absolute_file_path,encoding='utf-8')

US_Unemployment.info()
US_Unemployment

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 3621 entries, 0 to 3620
Data columns (total 3 columns):
 #   Column              Non-Null Count  Dtype  
---  ------              --------------  -----  
 0   first_day_of_month  3621 non-null   object 
 1   state               3621 non-null   object 
 2   unemployment_rate   3621 non-null   float64
dtypes: float64(1), object(2)
memory usage: 85.0+ KB


US_Unemployment.isna().sum()

first_day_of_month    0
state                 0
unemployment_rate     0
dtype: int64


US_Unemployment['first_day_of_month'] = pd.to_datetime(US_Unemployment['first_day_of_month'])
mask = US_Unemployment['first_day_of_month'].dt.year == 2021
US_Unemployment = US_Unemployment[mask]
US_Unemployment.info()
US_Unemployment

<class 'pandas.core.frame.DataFrame'>
Int64Index: 612 entries, 48 to 3609
Data columns (total 3 columns):
 #   Column              Non-Null Count  Dtype         
---  ------              --------------  -----         
 0   first_day_of_month  612 non-null    datetime64[ns]
 1   state               612 non-null    object        
 2   unemployment_rate   612 non-null    float64       
dtypes: datetime64[ns](1), float64(1), object(1)
memory usage: 19.1+ KB


US_Unemployment['year'] = US_Unemployment['first_day_of_month'].dt.year
US_Unemployment = US_Unemployment.groupby(['state', 'year'])['unemployment_rate'].mean().reset_index()

US_Unemployment.drop(columns=['year'], inplace=True)
US_Unemployment.rename(columns={'state': 'State', 'unemployment_rate': 'Unemployment'}, inplace=True)

US_Unemployment

/tmp/ipykernel_15/1859975808.py:1: SettingWithCopyWarning: 
A value is trying to be set on a copy of a slice from a DataFrame.
Try using .loc[row_indexer,col_indexer] = value instead

See the caveats in the documentation: https://pandas.pydata.org/pandas-docs/stable/user_guide/indexing.html#returning-a-view-versus-a-copy
  US_Unemployment['year'] = US_Unemployment['first_day_of_month'].dt.year


excel_file_path = 'NST-EST2022-POP.xlsx'
absolute_file_path = os.path.join(current_directory, excel_file_path)

US_Population = pd.read_excel(absolute_file_path,skiprows=3,skipfooter=7)

US_Population.info()
US_Population

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 56 entries, 0 to 55
Data columns (total 5 columns):
 #   Column      Non-Null Count  Dtype 
---  ------      --------------  ----- 
 0   Unnamed: 0  56 non-null     object
 1   Unnamed: 1  56 non-null     int64 
 2   2020        56 non-null     int64 
 3   2021        56 non-null     int64 
 4   2022        56 non-null     int64 
dtypes: int64(4), object(1)
memory usage: 2.3+ KB


US_Population.isna().sum()

Unnamed: 0    0
Unnamed: 1    0
2020          0
2021          0
2022          0
dtype: int64


US_Population.drop(columns=['Unnamed: 1'], inplace=True)
US_Population = US_Population.drop(US_Population.columns[[1, 3]], axis=1)
US_Population = US_Population.drop(range(5), axis=0)
US_Population.rename(columns={"Unnamed: 0": "State"}, inplace=True)
US_Population.head()


US_Population['State'] = US_Population['State'].str.replace(".", "")
US_Population.reset_index(drop=True, inplace=True)
US_Population

/tmp/ipykernel_15/1857523339.py:1: FutureWarning: The default value of regex will change from True to False in a future version. In addition, single character regular expressions will *not* be treated as literal strings when regex=True.
  US_Population['State'] = US_Population['State'].str.replace(".", "")


US_merged = pd.merge(US_States, US_GDP_State, on='State')
US_merged = pd.merge(US_merged, US_Unemployment, on='State')
US_merged = pd.merge(US_merged, US_Population, on='State')
US_merged.info()
US_merged

<class 'pandas.core.frame.DataFrame'>
Int64Index: 51 entries, 0 to 50
Data columns (total 5 columns):
 #   Column        Non-Null Count  Dtype  
---  ------        --------------  -----  
 0   State         51 non-null     object 
 1   Abbreviation  51 non-null     object 
 2   GDP_2021      51 non-null     float64
 3   Unemployment  51 non-null     float64
 4   2021          51 non-null     int64  
dtypes: float64(2), int64(1), object(2)
memory usage: 2.4+ KB


US_merged = US_merged.rename(columns={'GDP_2021': 'GDP($)', 'Unemployment': 'Unemployment(%)'})
US_merged.columns.values[4] = "Population"
US_merged


Fortune_1000.reset_index(drop=True, inplace=True)
Fortune_1000_sec.reset_index(drop=True, inplace=True)
Fortune_1000["Assets"] = Fortune_1000_sec["assets"]
Fortune_1000.info()
Fortune_1000

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1000 entries, 0 to 999
Data columns (total 14 columns):
 #   Column       Non-Null Count  Dtype  
---  ------       --------------  -----  
 0   Company      1000 non-null   object 
 1   Revenue      1000 non-null   float64
 2   Profit       1000 non-null   float64
 3   Employees    1000 non-null   int64  
 4   Sector       1000 non-null   object 
 5   City         1000 non-null   object 
 6   State        1000 non-null   object 
 7   New_Entry    1000 non-null   object 
 8   CEO_Founder  1000 non-null   object 
 9   CEO_Woman    1000 non-null   object 
 10  Profitable   1000 non-null   object 
 11  CEO          1000 non-null   object 
 12  Website      1000 non-null   object 
 13  Assets       1000 non-null   float64
dtypes: float64(3), int64(1), object(10)
memory usage: 109.5+ KB


new_column_order = ['Company', 'Revenue', 'Assets','Profit','Employees', 'Sector', 'State','City', 'CEO_Founder', 'CEO_Woman','New_Entry', 'Profitable', 'CEO', 'Website']
Fortune_1000 = Fortune_1000.reindex(columns=new_column_order)
Fortune_1000


top_10_revenues = Fortune_1000.nlargest(10, 'Revenue')

fig = px.bar(top_10_revenues, x='Company', y='Revenue', labels={'Revenue': 'Revenues (millions $)'}, title='Top 10 Companies by Revenues')
fig.update_layout(xaxis_tickangle=-45)
fig.show()


revenue_bins = np.arange(0, 600000, 20000)

fig = px.histogram(Fortune_1000, x='Revenue', nbins=50, labels={'Revenue': 'Revenues (millions $)'}, title='Distribution of Revenues')
fig.update_layout(xaxis_range=[0, Fortune_1000['Revenue'].max()], xaxis_tickangle=-45)
fig.show()


fig = px.box(Fortune_1000, x='Revenue')
fig.update_layout(title='Distribution of Revenues', xaxis_title='Revenues (millions $)', yaxis_title='Distribution')
fig.show()


sector_summary = Fortune_1000['Sector'].value_counts()

fig = px.bar(sector_summary, x=sector_summary.index, y=sector_summary.values, color=sector_summary.index)
fig.update_layout(xaxis_title='Sector', yaxis_title='Frequency', title='Distribution of Companies by Sector',
                  xaxis_tickangle=-90)
fig.show()


revenues_by_sector = Fortune_1000.groupby('Sector')['Revenue'].sum()

sectors = revenues_by_sector.index
total_revenues = revenues_by_sector.values

unique_sectors = Fortune_1000['Sector'].unique()

colors = plt.cm.tab20(np.linspace(0, 1, len(unique_sectors)))

plt.figure(figsize=(12, 6))
for sector, color in zip(unique_sectors, colors):
    sector_data = Fortune_1000[Fortune_1000['Sector'] == sector]
    frequencies = np.arange(1, len(sector_data) + 1)
    plt.scatter(frequencies, sector_data['Revenue'], color=color, label=sector)

plt.xlabel('Frequency')
plt.ylabel('Revenues (millions $)')
plt.title('Companies Revenues by Sector')
plt.xticks(rotation=90)
plt.yscale('log') 
plt.legend()
plt.tight_layout()
plt.show()


revenues_by_sector = Fortune_1000.groupby('Sector')['Revenue'].sum()
sectors = revenues_by_sector.index
total_revenues = revenues_by_sector.values

fig = px.bar(x=sectors, y=total_revenues, color=sectors)
fig.update_layout(
    title='Total Revenues by Sector',
    xaxis=dict(title='Sector'),
    yaxis=dict(title='Total Revenues (millions $)'),
    xaxis_tickangle=-45
)
fig.show()


fig = go.Figure(data=[go.Pie(labels=sectors, values=total_revenues, marker=dict(colors=colors), textinfo='label')])
fig.update_layout(title='Total Revenues by Sector')
fig.show()


revenues = Fortune_1000['Revenue']
profits = Fortune_1000['Profit']

slope, intercept, r_value, p_value, std_err = stats.linregress(revenues, profits)
regression_line = lambda x: slope * x + intercept
correlation_coefficient = np.corrcoef(revenues, profits)[0, 1]
coefficient_of_determination = r_value**2

scatter_trace = go.Scatter(
    x=revenues,
    y=profits,
    mode='markers',
    marker=dict(color='blue', opacity=0.5),
    name='Data'
)

regression_trace = go.Scatter(
    x=revenues,
    y=regression_line(revenues),
    mode='lines',
    line=dict(color='red'),
    name='Regression Line'
)

layout = go.Layout(
    title='Revenues vs Profits',
    xaxis=dict(title='Revenues (millions $)'),
    yaxis=dict(title='Profits (millions $)'),
    showlegend=False,
    annotations=[
        dict(
            x=0.05,
            y=0.95,
            xref='paper',
            yref='paper',
            text=f'y = {slope:.2f}x + {intercept:.2f}',
            showarrow=False,
            font=dict(size=12),
            align='left'
        ),
        dict(
            x=0.05,
            y=0.90,
            xref='paper',
            yref='paper',
            text=f'Correlation (r): {correlation_coefficient:.2f}',
            showarrow=False,
            font=dict(size=12),
            align='left'
        ),
        dict(
            x=0.05,
            y=0.85,
            xref='paper',
            yref='paper',
            text=f'Squared correlation (R^2): {coefficient_of_determination:.2f}',
            showarrow=False,
            font=dict(size=12),
            align='left'
        )
    ]
)

fig = go.Figure(data=[scatter_trace, regression_trace], layout=layout)
fig.show()


top_10_profitable = Fortune_1000.nlargest(10, 'Profit')

bar_trace = go.Bar(
    x=top_10_profitable['Company'],
    y=top_10_profitable['Profit'],
    marker=dict(color='blue')
)

layout = go.Layout(
    title='Top 10 Most Profitable Companies',
    xaxis=dict(title='Company'),
    yaxis=dict(title='Profits (millions $)'),
    showlegend=False,
    xaxis_tickangle=-90
)

fig = go.Figure(data=[bar_trace], layout=layout)

fig.show()


histogram_trace = go.Histogram(
    x=Fortune_1000['Profit'],
    nbinsx=50,
    marker=dict(color='blue', line=dict(color='black', width=1))
)

layout = go.Layout(
    title='Distribution of Profits',
    xaxis=dict(title='Profits (millions $)'),
    yaxis=dict(title='Frequency'),
    showlegend=False
)

fig = go.Figure(data=[histogram_trace], layout=layout)
fig.show()


plt.figure(figsize=(10, 6))
sns.kdeplot(Fortune_1000['Profit'], fill=True)
plt.xlabel('Profits (millions $)')
plt.ylabel('Density')
plt.title('Density Plot of Profits')
plt.show()


profits_by_sector = Fortune_1000.groupby('Sector')['Profit'].sum()
sectors = profits_by_sector.index
total_profits = profits_by_sector.values

colors = [
    '#1f77b4', '#ff7f0e', '#2ca02c', '#d62728', '#9467bd',
    '#8c564b', '#e377c2', '#7f7f7f', '#bcbd22', '#17becf',
    '#b0c4de', '#ffb6c1', '#c0c0c0', '#66cdaa', '#ffa500',
    '#ffd700', '#d2691e', '#40e0d0', '#808080', '#008080',
    '#000080', '#800080', '#008000', '#800000', '#0000ff'
]

bar_trace = go.Bar(
    x=sectors,
    y=total_profits,
    marker=dict(color=colors[:len(sectors)])
)

layout = go.Layout(
    title='Total Profits by Sector',
    xaxis=dict(title='Sector'),
    yaxis=dict(title='Profit'),
    xaxis_tickangle=-45
)

fig = go.Figure(data=[bar_trace], layout=layout)
fig.show()


profits_by_sector = Fortune_1000.groupby('Sector')['Profit'].sum()
sectors = profits_by_sector.index
total_profits = profits_by_sector.values

colors = [
    '#1f77b4', '#ff7f0e', '#2ca02c', '#d62728', '#9467bd',
    '#8c564b', '#e377c2', '#7f7f7f', '#bcbd22', '#17becf',
    '#b0c4de', '#ffb6c1', '#c0c0c0', '#66cdaa', '#ffa500',
    '#ffd700', '#d2691e', '#40e0d0', '#808080', '#008080',
    '#000080', '#800080', '#008000', '#800000', '#0000ff'
]

pie_trace = go.Pie(
    labels=sectors,
    values=total_profits,
    marker=dict(colors=colors[:len(sectors)]),
    textinfo='none'  
)

layout = go.Layout(
    title='Total Profits by Sector'
)

fig = go.Figure(data=[pie_trace], layout=layout)
fig.show()


Fortune_1000['Profit_Margin(%)'] = (Fortune_1000['Profit'] / Fortune_1000['Revenue']) * 100
Fortune_1000


profit_margins_by_sector = Fortune_1000.groupby('Sector')['Profit_Margin(%)'].mean()
sectors = profit_margins_by_sector.index
margin_values = profit_margins_by_sector.values

colors = [
    '#1f77b4', '#ff7f0e', '#2ca02c', '#d62728', '#9467bd',
    '#8c564b', '#e377c2', '#7f7f7f', '#bcbd22', '#17becf',
    '#b0c4de', '#ffb6c1', '#c0c0c0', '#66cdaa', '#ffa500',
    '#ffd700', '#d2691e', '#40e0d0', '#808080', '#008080',
    '#000080', '#800080', '#008000', '#800000', '#0000ff'
]

bar_trace = go.Bar(
    x=sectors,
    y=margin_values,
    marker=dict(color=colors[:len(sectors)])
)

layout = go.Layout(
    xaxis=dict(title='Sector'),
    yaxis=dict(title='Profit Margin (%)'),
    title='Profit Margins by Sector',
    xaxis_tickangle=-45
)

fig = go.Figure(data=[bar_trace], layout=layout)
fig.show()


Fortune_1000['ROA(%)'] = (Fortune_1000['Profit'] / Fortune_1000['Assets']) * 100
Fortune_1000


top_10_assets = Fortune_1000.nlargest(10, 'Assets')

bar_trace = go.Bar(
    x=top_10_assets['Company'],
    y=top_10_assets['Assets']
)

layout = go.Layout(
    xaxis=dict(title='Company'),
    yaxis=dict(title='Total Assets'),
    title='Top 10 Companies by Total Assets',
    xaxis_tickangle=-45
)

fig = go.Figure(data=[bar_trace], layout=layout)
fig.show()


assets_by_sector = Fortune_1000.groupby('Sector')['Assets'].sum().reset_index()

fig = px.bar(assets_by_sector, x='Sector', y='Assets', color='Sector', title='Total Assets by Sector',
             labels={'Assets': 'Total Assets'}, color_discrete_sequence=colors)
fig.update_layout(xaxis_tickangle=-45)
fig.show()


assets_by_sector = Fortune_1000.groupby('Sector')['Assets'].sum().reset_index()
sectors = assets_by_sector['Sector']
assets_values = assets_by_sector['Assets']

fig = go.Figure(data=[go.Pie(labels=sectors, values=assets_values, marker=dict(colors=colors), textinfo='none')])
fig.update_layout(title='Total Assets by Sector')
fig.show()


roa_by_sector = Fortune_1000.groupby('Sector')['ROA(%)'].mean()
sectors = roa_by_sector.index
roa_values = roa_by_sector.values

colors = ['#1f77b4', '#ff7f0e', '#2ca02c', '#d62728', '#9467bd',
          '#8c564b', '#e377c2', '#7f7f7f', '#bcbd22', '#17becf',
          '#b0c4de', '#ffb6c1', '#c0c0c0', '#66cdaa', '#ffa500',
          '#ffd700', '#d2691e', '#40e0d0', '#808080', '#008080',
          '#000080', '#800080', '#008000', '#800000', '#0000ff']

bar_trace = go.Bar(
    x=sectors,
    y=roa_values,
    marker=dict(color=colors)
)

layout = go.Layout(
    xaxis=dict(title='Sector'),
    yaxis=dict(title='Return on Assets (ROA)'),
    title='ROA by Sector',
    xaxis_tickangle=-45
)

fig = go.Figure(data=[bar_trace], layout=layout)
fig.show()


correlation_matrix = Fortune_1000[['Assets', 'Revenue', 'Profit']].corr()

plt.figure(figsize=(8, 6))
sns.heatmap(correlation_matrix, annot=True, cmap='coolwarm', vmin=-1, vmax=1)
plt.title('Correlation Matrix: Assets, Revenues, and Profits')
plt.tight_layout()
plt.show()


top_10_employees = Fortune_1000.nlargest(10, 'Employees')

fig = px.bar(top_10_employees, x='Company', y='Employees', color='Company')
fig.update_layout(
    xaxis_title='Company',
    yaxis_title='Number of Employees',
    title='Top 10 Companies by Number of Employees',
    xaxis_tickangle=-45
)

fig.show()


Fortune_1000['Revenue_per_Employee'] = Fortune_1000['Revenue'] / Fortune_1000['Employees']
top_10_revenue_per_employee = Fortune_1000.nlargest(10, 'Revenue_per_Employee')

fig = px.bar(top_10_revenue_per_employee, x='Company', y='Revenue_per_Employee', color='Company')
fig.update_layout(
    xaxis_title='Company',
    yaxis_title='Revenue per Employee (millions $)',
    title='Top 10 Companies by Revenue per Employee',
    xaxis_tickangle=-45
)

fig.show()


revenues = Fortune_1000['Revenue']
employees = Fortune_1000['Employees']

slope, intercept, r_value, p_value, std_err = stats.linregress(employees, revenues)
r_squared = r_value ** 2

fig = go.Figure()

fig.add_trace(go.Scatter(
    x=employees,
    y=revenues,
    mode='markers',
    marker=dict(color='blue', opacity=0.5),
    name='Data Points'
))

x = np.linspace(0, employees.max(), 100)
y = intercept + slope * x
fig.add_trace(go.Scatter(
    x=x,
    y=y,
    mode='lines',
    line=dict(color='red'),
    name='Regression Line'
))

fig.update_layout(
    xaxis_title='Number of Employees',
    yaxis_title='Revenues (millions $)',
    title='Correlation between Revenues and Number of Employees',
    showlegend=True
)

regression_equation = f'Regression Line: y = {slope:.2f}x + {intercept:.2f}'
correlation_text = f'Correlation (r): {r_value:.2f}'
r_squared_text = f'R-squared: {r_squared:.2f}'

fig.add_annotation(
    xref='paper',
    yref='paper',
    x=0.98,
    y=0.9,
    text=regression_equation,
    showarrow=False,
    font=dict(color='white'),
    align='right',
    bgcolor='black',
    bordercolor='black',
    borderwidth=2
)

fig.add_annotation(
    xref='paper',
    yref='paper',
    x=0.98,
    y=0.85,
    text=correlation_text,
    showarrow=False,
    font=dict(color='white'),
    align='right',
    bgcolor='black',
    bordercolor='black',
    borderwidth=2
)

fig.add_annotation(
    xref='paper',
    yref='paper',
    x=0.98,
    y=0.8,
    text=r_squared_text,
    showarrow=False,
    font=dict(color='white'),
    align='right',
    bgcolor='black',
    bordercolor='black',
    borderwidth=2
)

fig.show()


Fortune_1000_copy = cp.deepcopy(Fortune_1000)
Fortune_1000_copy.head()


US_merged_copy = cp.deepcopy(US_merged)
US_merged_copy.head()


current_dir = os.getcwd()
shapefile_path = os.path.join(current_dir, 'US_State_Boundaries.shp')
us_map = gpd.read_file(shapefile_path)

state_counts = Fortune_1000_copy['State'].value_counts()

all_states = pd.Series(0, index=us_map['STATE_ABBR'], name='State_Count')

all_states.update(state_counts)

merged_map = us_map.merge(all_states, left_on='STATE_ABBR', right_index=True, how='left')

color_map = LinearColormap(['white', 'blue'], vmin=0, vmax=merged_map['State_Count'].max(), caption='State Count')

m = folium.Map(location=[37, -95], zoom_start=4)

folium.GeoJson(merged_map,
               name='Choropleth',
               style_function=lambda feature: {
                   'fillColor': color_map(feature['properties']['State_Count']),
                   'color': 'black',
                   'weight': 0.8,
                   'fillOpacity': 0.7
               },
               highlight_function=lambda x: {'weight': 3},
               tooltip=folium.features.GeoJsonTooltip(fields=['NAME', 'State_Count'],
                                                      aliases=['State', 'Count'],
                                                      sticky=True,
                                                      style='background-color: white; color: #333333;'),
               show=False
               ).add_to(m)

color_map.add_to(m)
m


states = ['CA', 'TX', 'NY', 'IL', 'OH', 'PA']

filtered_df = Fortune_1000[Fortune_1000['State'].isin(states)]

total_companies = len(filtered_df)

print("Total number of companies from CA, TX, NY, IL, OH, PA:", total_companies)

Total number of companies from CA, TX, NY, IL, OH, PA: 476


revenue_by_state = Fortune_1000_copy.groupby('State')['Revenue'].sum().reset_index()
revenue_by_state = revenue_by_state.sort_values('Revenue', ascending=False)

fig = go.Figure(data=go.Bar(x=revenue_by_state['State'], y=revenue_by_state['Revenue']))

fig.update_layout(
    title='Total Revenue by State',
    xaxis_title='State',
    yaxis_title='Total Revenue',
    xaxis_tickangle=-45
)

fig.show()


revenue_by_state = Fortune_1000_copy.groupby('State')['Revenue'].sum().reset_index()

current_dir = os.getcwd()
shapefile_path = os.path.join(current_dir, 'US_State_Boundaries.shp')
us_map = gpd.read_file(shapefile_path)

merged_map = us_map.merge(revenue_by_state, left_on='STATE_ABBR', right_on='State', how='left')

fig = go.Figure(data=go.Choropleth(
    locations=merged_map['STATE_ABBR'],
    z=merged_map['Revenue'],
    locationmode='USA-states',
    colorscale='Blues',
    colorbar_title='Revenues',
))

fig.update_layout(
    title_text='Revenues per State (Millions $)',
    geo_scope='usa',
)

fig.show()


states = ['CA', 'TX', 'NY', 'IL', 'OH', 'PA']

filtered_df = Fortune_1000[Fortune_1000['State'].isin(states)]

total_revenue_selected = filtered_df['Revenue'].sum()

print("Total revenue of companies from CA, TX, NY, IL, OH, PA: $", total_revenue_selected, " millions.", sep="")

Total revenue of companies from CA, TX, NY, IL, OH, PA: $8910237.5 millions.


total_revenue = Fortune_1000['Revenue'].sum()

print("Total revenue of all Fortune 1000 companies: $", total_revenue, " millions.", sep="")

Total revenue of all Fortune 1000 companies: $17986801.4 millions.


8910237.5/17986801.4

0.4953764319652743


current_dir = os.getcwd()
shapefile_path = os.path.join(current_dir, 'US_State_Boundaries.shp')
us_map = gpd.read_file(shapefile_path)

merged_map = us_map.merge(US_merged_copy[['Abbreviation', 'Population']], left_on='STATE_ABBR', right_on='Abbreviation', how='left')

fig = go.Figure(data=go.Choropleth(
    locations=merged_map['STATE_ABBR'],
    z=merged_map['Population'],
    locationmode='USA-states',
    colorscale='Blues',
    colorbar_title='Population',
))

fig.update_layout(
    title_text='Population per State',
    geo_scope='usa',
)

fig.show()


current_dir = os.getcwd()
shapefile_path = os.path.join(current_dir, 'US_State_Boundaries.shp')
us_map = gpd.read_file(shapefile_path)

merged_map = us_map.merge(US_merged_copy[['Abbreviation', 'GDP($)']], left_on='STATE_ABBR', right_on='Abbreviation', how='left')

fig = go.Figure(data=go.Choropleth(
    locations=merged_map['STATE_ABBR'],
    z=merged_map['GDP($)'],
    locationmode='USA-states',
    colorscale='Blues',
    colorbar_title='GDP',
))

fig.update_layout(
    title_text='GDP per State (Millions $)',
    geo_scope='usa',
)

fig.show()


US_merged_copy['GDP_per_capita'] = US_merged_copy['GDP($)'] / US_merged_copy['Population']

current_dir = os.getcwd()
shapefile_path = os.path.join(current_dir, 'US_State_Boundaries.shp')
us_map = gpd.read_file(shapefile_path)

merged_map = us_map.merge(US_merged_copy[['Abbreviation', 'GDP_per_capita']], left_on='STATE_ABBR', right_on='Abbreviation', how='left')

merged_map = merged_map[merged_map['NAME'] != 'District of Columbia']

fig = go.Figure(data=go.Choropleth(
    locations=merged_map['STATE_ABBR'],
    z=merged_map['GDP_per_capita'],
    locationmode='USA-states',
    colorscale='Blues',
    colorbar_title='GDP per capita',
))

fig.update_layout(
    title_text='GDP per Capita in US (Millions $)',
    geo_scope='usa',
)

fig.show()


US_merged_copy[US_merged_copy.State=="District of Columbia"]


current_dir = os.getcwd()
shapefile_path = os.path.join(current_dir, 'US_State_Boundaries.shp')
us_map = gpd.read_file(shapefile_path)

merged_map = us_map.merge(US_merged_copy[['Abbreviation', 'Unemployment(%)']], left_on='STATE_ABBR', right_on='Abbreviation', how='left')

fig = go.Figure(data=go.Choropleth(
    locations=merged_map['STATE_ABBR'],
    z=merged_map['Unemployment(%)'],
    locationmode='USA-states',
    colorscale='Blues',
    colorbar_title='Unemployment(%)',
))

fig.update_layout(
    title_text='Unemployment rate by State (%)',
    geo_scope='usa',
)

fig.show()


num_companies_by_state = Fortune_1000_copy['State'].value_counts().reset_index()
num_companies_by_state.columns = ['State', 'Number_of_Companies']

merged_df = US_merged_copy.merge(num_companies_by_state, left_on='Abbreviation', right_on='State', how='left')

merged_df['Number_of_Companies'] = merged_df['Number_of_Companies'].fillna(0)

fig = px.scatter(merged_df, x='Population', y='GDP($)', size='Number_of_Companies',
                 color='State_x', hover_data=['State_x'], title='Relationship between Population, State GDP, and Number of Fortune 1000 Companies')

fig.update_layout(
    xaxis_title='Population',
    yaxis_title='State GDP',
    showlegend=True,
    hovermode='closest'
)

fig.show()


merged_df['Population'] = merged_df['Population'] / 1e6

fig = px.scatter(merged_df, x='Population', y='Number_of_Companies', size='GDP($)',
                 color='State_x', hover_data=['State_x'], title='Relationship between Population and Number of Fortune 1000 Companies')

slope, intercept, r_value, p_value, std_err = stats.linregress(merged_df['Population'], merged_df['Number_of_Companies'])
line = slope * merged_df['Population'] + intercept

fig.add_trace(px.line(x=merged_df['Population'], y=line).data[0])

r_squared = r_value**2

equation_text = f"y = {slope:.2f}x + {intercept:.2f}"
correlation_text = f"Correlation (r): {r_value:.2f}"
r_squared_text = f"R-squared: {r_squared:.2f}"

fig.add_annotation(x=0.95, y=0.9, xref="paper", yref="paper",
                   text=equation_text, showarrow=False, font=dict(size=12))
fig.add_annotation(x=0.95, y=0.8, xref="paper", yref="paper",
                   text=correlation_text, showarrow=False, font=dict(size=12))
fig.add_annotation(x=0.95, y=0.7, xref="paper", yref="paper",
                   text=r_squared_text, showarrow=False, font=dict(size=12))

fig.update_layout(
    xaxis_title='Population (Millions)',
    yaxis_title='Number of Fortune 1000 Companies',
    showlegend=True,
    hovermode='closest'
)

fig.show()


merged_df['GDP($)'] = merged_df['GDP($)'] / 1e6
fig = px.scatter(merged_df, x='GDP($)', y='Number_of_Companies', size='Population',
                 color='State_x', hover_data=['State_x'], title='Relationship between GDP and Number of Fortune 1000 Companies')

slope, intercept, r_value, p_value, std_err = stats.linregress(merged_df['GDP($)'], merged_df['Number_of_Companies'])
line = slope * merged_df['GDP($)'] + intercept

fig.add_trace(px.line(x=merged_df['GDP($)'], y=line).data[0])

r_squared = r_value**2

equation_text = f"y = {slope:.2f}x + {intercept:.2f}"
correlation_text = f"Correlation (r): {r_value:.2f}"
r_squared_text = f"R-squared: {r_squared:.2f}"

fig.add_annotation(x=0.95, y=0.9, xref="paper", yref="paper",
                   text=equation_text, showarrow=False, font=dict(size=12))
fig.add_annotation(x=0.95, y=0.8, xref="paper", yref="paper",
                   text=correlation_text, showarrow=False, font=dict(size=12))
fig.add_annotation(x=0.95, y=0.7, xref="paper", yref="paper",
                   text=r_squared_text, showarrow=False, font=dict(size=12))

fig.update_layout(
    xaxis_title='GDP (Millions $)',
    yaxis_title='Number of Fortune 1000 Companies',
    showlegend=True,
    hovermode='closest'
)

fig.show()


fig = px.scatter(merged_df, x='GDP_per_capita', y='Number_of_Companies', size='Population',
                 color='State_x', hover_data=['State_x'], title='Relationship between GDP per capita and Number of Fortune 1000 Companies')

slope, intercept, r_value, p_value, std_err = stats.linregress(merged_df['GDP_per_capita'], merged_df['Number_of_Companies'])
line = slope * merged_df['GDP_per_capita'] + intercept

fig.add_trace(px.line(x=merged_df['GDP_per_capita'], y=line).data[0])

r_squared = r_value**2

equation_text = f"y = {slope:.2f}x + {intercept:.2f}"
correlation_text = f"Correlation (r): {r_value:.2f}"
r_squared_text = f"R-squared: {r_squared:.2f}"

fig.add_annotation(x=0.95, y=0.9, xref="paper", yref="paper",
                   text=equation_text, showarrow=False, font=dict(size=12))
fig.add_annotation(x=0.95, y=0.8, xref="paper", yref="paper",
                   text=correlation_text, showarrow=False, font=dict(size=12))
fig.add_annotation(x=0.95, y=0.7, xref="paper", yref="paper",
                   text=r_squared_text, showarrow=False, font=dict(size=12))

fig.update_layout(
    xaxis_title='GDP per capita (Millions $)',
    yaxis_title='Number of Fortune 1000 Companies',
    showlegend=True,
    hovermode='closest'
)

fig.show()


fig = px.scatter(merged_df, x='Unemployment(%)', y='Number_of_Companies', size='Population',
                 color='State_x', hover_data=['State_x'], title='Relationship between Unemployment Rates and Number of Fortune 1000 Companies')

slope, intercept, r_value, p_value, std_err = stats.linregress(merged_df['Unemployment(%)'], merged_df['Number_of_Companies'])
line = slope * merged_df['Unemployment(%)'] + intercept

fig.add_trace(px.line(x=merged_df['Unemployment(%)'], y=line).data[0])

r_squared = r_value**2

equation_text = f"y = {slope:.2f}x + {intercept:.2f}"
correlation_text = f"Correlation (r): {r_value:.2f}"
r_squared_text = f"R-squared: {r_squared:.2f}"

fig.add_annotation(x=0.95, y=0.9, xref="paper", yref="paper",
                   text=equation_text, showarrow=False, font=dict(size=12))
fig.add_annotation(x=0.95, y=0.8, xref="paper", yref="paper",
                   text=correlation_text, showarrow=False, font=dict(size=12))
fig.add_annotation(x=0.95, y=0.7, xref="paper", yref="paper",
                   text=r_squared_text, showarrow=False, font=dict(size=12))

fig.update_layout(
    xaxis_title='Unemployment Rate (%)',
    yaxis_title='Number of Fortune 1000 Companies',
    showlegend=True,
    hovermode='closest'
)

fig.show()


Fortune_1000_copy2 = cp.deepcopy(Fortune_1000_copy)

founder_ceo_count = Fortune_1000_copy2['CEO_Founder'].value_counts()
women_ceo_count = Fortune_1000_copy2['CEO_Woman'].value_counts()
founder_women_ceo_count = Fortune_1000_copy2[(Fortune_1000_copy2['CEO_Founder'] == 'yes') & (Fortune_1000_copy2['CEO_Woman'] == 'yes')].shape[0]

print("Founder CEOs Count:")
print(founder_ceo_count)
print("\nWomen CEOs Count:")
print(women_ceo_count)
print("\nFounder and Women CEOs Count:")
print(founder_women_ceo_count)

Founder CEOs Count:
no     944
yes     56
Name: CEO_Founder, dtype: int64

Women CEOs Count:
no     917
yes     83
Name: CEO_Woman, dtype: int64

Founder and Women CEOs Count:
0


Fortune_1000_copy2 = cp.deepcopy(Fortune_1000_copy)
Fortune_1000_copy2['CEO_Type'] = 'Neither'
Fortune_1000_copy2.loc[Fortune_1000_copy2['CEO_Founder'] == 'yes', 'CEO_Type'] = 'Founder'
Fortune_1000_copy2.loc[Fortune_1000_copy2['CEO_Woman'] == 'yes', 'CEO_Type'] = 'Women'
Fortune_1000_copy2.loc[(Fortune_1000_copy2['CEO_Founder'] == 'yes') & (Fortune_1000_copy2['CEO_Woman'] == 'yes'), 'CEO_Type'] = 'Both'

colors = {'Neither': 'gray', 'Founder': 'blue', 'Women': 'purple', 'Both': 'green'}

fig = px.scatter(Fortune_1000_copy2, x='Revenue', y='Profit', color='CEO_Type', color_discrete_map=colors)
fig.update_traces(marker=dict(size=9))
fig.update_layout(title='Profits and Revenues by CEO features', xaxis_title='Revenues', yaxis_title='Profits')
fig.show()


ceo_type_counts = Fortune_1000_copy2.groupby(['Sector', 'CEO_Type']).size().unstack(fill_value=0)
colors = {'Neither': 'gray', 'Women': 'purple', 'Founder': 'blue'}

fig = go.Figure()

for ceo_type, color in colors.items():
    fig.add_trace(go.Bar(x=ceo_type_counts.index, y=ceo_type_counts[ceo_type],
                         name=ceo_type, marker_color=color))

fig.update_layout(title='Distribution of Fortune 1000 Companies by Sector',
                  xaxis_title='Sector',
                  yaxis_title='Frequency',
                  barmode='stack')

fig.show()

	company	rank_change	revenue	profit	num. of employees	sector	city	state	newcomer	ceo_founder	ceo_woman	profitable	prev_rank	CEO	Website	Ticker	Market Cap
rank
1	Walmart	0.0	572754.0	13673.0	2300000.0	Retailing	Bentonville	AR	no	no	no	yes	1.0	C. Douglas McMillon	https://www.stock.walmart.com	WMT	352037
2	Amazon	0.0	469822.0	33364.0	1608000.0	Retailing	Seattle	WA	no	no	no	yes	2.0	Andrew R. Jassy	www.amazon.com	AMZN	1202717
3	Apple	0.0	365817.0	94680.0	154000.0	Technology	Cupertino	CA	no	no	no	yes	3.0	Timothy D. Cook	www.apple.com	AAPL	2443962
4	CVS Health	0.0	292111.0	7910.0	258000.0	Health Care	Woonsocket	RI	no	no	yes	yes	4.0	Karen Lynch	https://www.cvshealth.com	CVS	125204
5	UnitedHealth Group	0.0	287597.0	17285.0	350000.0	Health Care	Minnetonka	MN	no	no	no	yes	5.0	Andrew P. Witty	www.unitedhealthgroup.com	UNH	500468
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
996	Vizio Holding	0.0	2124.0	-39.4	800.0	Industrials	Irvine	CA	no	yes	no	no		William W. Wang	https://www.vizio.com	VZIO	1705.1
997	1-800-Flowers.com	0.0	2122.2	118.7	4800.0	Retailing	Jericho	NY	no	no	no	yes		Christopher G. McCann	https://www.1800flowers.com	FLWS	830
998	Cowen	0.0	2112.8	295.6	1534.0	Financials	New York	NY	no	no	no	yes		Jeffrey Solomon	https://www.cowen.com	COWN	1078
999	Ashland	0.0	2111.0	220.0	4100.0	Chemicals	Wilmington	DE	no	no	no	yes		Guillermo Novo	https://www.ashland.com	ASH	5601.9
1000	DocuSign	0.0	2107.2	-70.0	7461.0	Technology	San Francisco	CA	no	no	no	no		Allan C. Thygesen	https://www.docusign.com	DOCU	21302.8

	profit	num. of employees	Ticker	Market Cap
rank
42	1280.9	53586.0	NaN	NaN
72	277.1	14344.0	NaN	-
76	4412.2	232000.0	NaN	-
78	3068.0	45000.0	NaN	NaN
80	1617.2	24134.0	NaN	NaN
90	4060.7	15065.0	NaN	-
95	554.0	9941.0	NaN	NaN
96	3300.0	37335.0	NaN	-
97	977.8	7585.0	NaN	-
100	319.3	10052.0	NaN	-
232	287.4	9000.0	NaN	NaN
247	288.8	9150.0	NaN	NaN
251	734.5	13590.0	NaN	NaN
264	-366.8	11787.0	NaN	NaN
266	1102.0	3861.0	NaN	NaN
303	1605.0	50000.0	NaN	-
313	753.0	28800.0	NaN	NaN
324	579.0	5739.0	NaN	NaN
339	1318.4	6441.0	NaN	NaN
351	2530.2	3256.0	NaN	NaN
368	1130.1	5805.0	NaN	NaN
372	361.2	2538.0	NaN	NaN
399	262.4	8800.0	NaN	-
418	2842.4	5560.0	NaN	NaN
464	311.5	6941.0	NaN	NaN
499	NaN	15640.0	FYBR	6763.1
535	NaN	1300.0	CHK	11135.9
539	555.6	25150.0	NaN	27492.2
559	665.9	21700.0	NaN	3088.7
597	-221.4	7500.0	NaN	30976.8
602	622.3	4100.0	NaN	NaN
623	455.1	17662.0	NaN	4185.4
647	522.9	3194.0	NaN	NaN
650	739.9	4064.0	NaN	NaN
659	-165.1	8900.0	NaN	NaN
660	699.3	4545.0	NaN	5084.1
680	-27.0	6100.0	NaN	1856.2
690	419.2	3149.0	NaN	NaN
710	199.0	9600.0	NaN	2519.4
714	260.8	3185.0	NaN	NaN
736	NaN	7600.0	GTX	463.9
748	78.3	2834.0	NaN	NaN
775	392.1	1157.0	NaN	NaN
789	213.8	1196.0	NaN	3056.2
815	-112.2	15000.0	NaN	6799.3
866	133.7	NaN	NaN	NaN
874	-104.2	2952.0	NaN	10463.5
878	50.7	1146.0	NaN	NaN
880	117.1	3510.0	NaN	NaN
907	320.1	2702.0	NaN	NaN
925	130.3	749.0	NaN	NaN
948	-85.2	1082.0	NaN	NaN

	company	revenue	profit	num. of employees	sector	city	state	newcomer	ceo_founder	ceo_woman	profitable	CEO	Website
rank
1	Walmart	572754.0	13673.0	2300000.0	Retailing	Bentonville	AR	no	no	no	yes	C. Douglas McMillon	https://www.stock.walmart.com
2	Amazon	469822.0	33364.0	1608000.0	Retailing	Seattle	WA	no	no	no	yes	Andrew R. Jassy	www.amazon.com
3	Apple	365817.0	94680.0	154000.0	Technology	Cupertino	CA	no	no	no	yes	Timothy D. Cook	www.apple.com
4	CVS Health	292111.0	7910.0	258000.0	Health Care	Woonsocket	RI	no	no	yes	yes	Karen Lynch	https://www.cvshealth.com
5	UnitedHealth Group	287597.0	17285.0	350000.0	Health Care	Minnetonka	MN	no	no	no	yes	Andrew P. Witty	www.unitedhealthgroup.com
...	...	...	...	...	...	...	...	...	...	...	...	...	...
996	Vizio Holding	2124.0	-39.4	800.0	Industrials	Irvine	CA	no	yes	no	no	William W. Wang	https://www.vizio.com
997	1-800-Flowers.com	2122.2	118.7	4800.0	Retailing	Jericho	NY	no	no	no	yes	Christopher G. McCann	https://www.1800flowers.com
998	Cowen	2112.8	295.6	1534.0	Financials	New York	NY	no	no	no	yes	Jeffrey Solomon	https://www.cowen.com
999	Ashland	2111.0	220.0	4100.0	Chemicals	Wilmington	DE	no	no	no	yes	Guillermo Novo	https://www.ashland.com
1000	DocuSign	2107.2	-70.0	7461.0	Technology	San Francisco	CA	no	no	no	no	Allan C. Thygesen	https://www.docusign.com

	company	revenue	profit	num. of employees	sector	city	state	newcomer	ceo_founder	ceo_woman	profitable	CEO	Website
rank
499	Frontier Communications	6411.0	NaN	15640.0	Telecommunications	Norwalk	CT	no	no	no	no	Nick Jeffery	https://www.frontier.com
535	Chesapeake Energy	5809.0	NaN	1300.0	Energy	Oklahoma City	OK	no	no	no	no	Domenic J. Dell'Osso Jr.	https://www.chk.com
736	Garrett Motion	3633.0	NaN	7600.0	Motor Vehicles & Parts	Plymouth	MI	no	no	no	no	Olivier Rabiller	https://www.garrettmotion.com

	Company	Revenue	Profit	Employees	Sector	City	State	New_Entry	CEO_Founder	CEO_Woman	Profitable	CEO	Website
rank
1	Walmart	572754.0	13673.0	2300000	Retailing	Bentonville	AR	no	no	no	yes	C. Douglas McMillon	https://www.stock.walmart.com
2	Amazon	469822.0	33364.0	1608000	Retailing	Seattle	WA	no	no	no	yes	Andrew R. Jassy	www.amazon.com
3	Apple	365817.0	94680.0	154000	Technology	Cupertino	CA	no	no	no	yes	Timothy D. Cook	www.apple.com
4	CVS Health	292111.0	7910.0	258000	Health Care	Woonsocket	RI	no	no	yes	yes	Karen Lynch	https://www.cvshealth.com
5	UnitedHealth Group	287597.0	17285.0	350000	Health Care	Minnetonka	MN	no	no	no	yes	Andrew P. Witty	www.unitedhealthgroup.com
...	...	...	...	...	...	...	...	...	...	...	...	...	...
996	Vizio Holding	2124.0	-39.4	800	Industrials	Irvine	CA	no	yes	no	no	William W. Wang	https://www.vizio.com
997	1-800-Flowers.com	2122.2	118.7	4800	Retailing	Jericho	NY	no	no	no	yes	Christopher G. McCann	https://www.1800flowers.com
998	Cowen	2112.8	295.6	1534	Financials	New York	NY	no	no	no	yes	Jeffrey Solomon	https://www.cowen.com
999	Ashland	2111.0	220.0	4100	Chemicals	Wilmington	DE	no	no	no	yes	Guillermo Novo	https://www.ashland.com
1000	DocuSign	2107.2	-70.0	7461	Technology	San Francisco	CA	no	no	no	no	Allan C. Thygesen	https://www.docusign.com

Introduction to Coding and Data Management - 2 | Project work - Jacopo Lazzari 894361¶

Summary¶

Libraries¶

Datasets reading and cleaning¶

Fortune 1000 2022 (Main Dataset)¶

Fortune 1000 2022 second Dataset¶

US GDP by State Dataset¶

US States Abbreviations Dataset¶

US Unemployment Rates by State Dataset¶

US Population by State Dataset¶

Datasets combining and reshaping¶

US Dataset¶

Fortune 1000 datasets joining¶

Data analysis and visualization¶

Financial performances and sectors analysis¶

Focus on the geographical dimension¶

Company policies¶

Conclusion¶

	company	revenue	profit	num. of employees	sector	city	state	newcomer	ceo_founder	ceo_woman	profitable	CEO	Website
rank
866	Univision Communciations	2841.0	133.7	NaN	Media	New York	NY	no	no	no	yes	Wade C. Davis	https://https://corporate.televisaunivision.com

	Name	Revenue	revenue(% change)	profits in millions	profits % change\r	assets	market value	change in rank of top 1000 companies	employees	change in rank(500 only)\r\n
rank in 2022
1	Walmart	$572,754	2.40%	$13,673	1.20%	$244,860	$409,795	-	2,300,000	-
2	Amazon	$469,822	21.70%	$33,364	56.40%	$420,549	$1,658,807.30	-	1,608,000	-
3	Apple	$365,817	33.30%	$94,680	64.90%	$351,002	$2,849,537.60	-	154,000	-
4	CVS Health	$292,111	8.70%	$7,910	10.20%	$232,999	$132,839.20	-	258,000	-
5	UnitedHealth Group	$287,597	11.80%	$17,285	12.20%	$212,206	$479,830.30	-	350,000	-
...	...	...	...	...	...	...	...	...	...	...
996	Vizio Holding	$2,124	4%	-$39.40	-138.40%	$935.80	$1,705.10	-	800	-
997	1-800-Flowers.com	$2,122.20	42.50%	$118.70	101.10%	$1,076.70	$830	-	4,800	-
998	Cowen	$2,112.80	30.20%	$295.60	36.60%	$8,748.80	$744.10	-	1,534	-
999	Ashland Global Holdings	$2,111	-11.20%	$220	-	$6,612	$5,601.90	-130	4,100	-
1,000	DocuSign	$2,107.20	45%	-$70	-	$2,541.30	$21,302.80	-	7,461	-

	GeoFips	GeoName	2021
0	0	United States *	23315081.0
1	1000	Alabama	254109.7
2	2000	Alaska	57349.4
3	4000	Arizona	420026.7
4	5000	Arkansas	148676.1
5	6000	California	3373240.7
6	8000	Colorado	436359.5
7	9000	Connecticut	298395.2
8	10000	Delaware	81160.0
9	11000	District of Columbia	153670.5
10	12000	Florida	1255558.3
11	13000	Georgia	691626.9
12	15000	Hawaii	91096.1
13	16000	Idaho	96282.8
14	17000	Illinois	945673.8
15	18000	Indiana	412975.2
16	19000	Iowa	216860.2
17	20000	Kansas	191380.6
18	21000	Kentucky	237182.0
19	22000	Louisiana	258571.3
20	23000	Maine	77963.3
21	24000	Maryland	443929.9
22	25000	Massachusetts	641332.2
23	26000	Michigan	572205.8
24	27000	Minnesota	412458.6
25	28000	Mississippi	127307.7
26	29000	Missouri	358572.0
27	30000	Montana	58699.8
28	31000	Nebraska	146285.4
29	32000	Nevada	194486.6
30	33000	New Hampshire	99673.3
31	34000	New Jersey	682945.9
32	35000	New Mexico	109582.8
33	36000	New York	1901296.5
34	37000	North Carolina	662120.8
35	38000	North Dakota	63559.6
36	39000	Ohio	756617.2
37	40000	Oklahoma	215336.3
38	41000	Oregon	272190.9
39	42000	Pennsylvania	844496.5
40	44000	Rhode Island	66570.9
41	45000	South Carolina	269802.5
42	46000	South Dakota	61684.7
43	47000	Tennessee	427125.5
44	48000	Texas	2051768.6
45	49000	Utah	225340.3
46	50000	Vermont	37103.8
47	51000	Virginia	604957.6
48	53000	Washington	677489.5
49	54000	West Virginia	85434.2
50	55000	Wisconsin	368611.3
51	56000	Wyoming	41510.2

	first_day_of_month	state	unemployment_rate
0	2017-01-01	California	5.2
1	2017-02-01	California	5.1
2	2017-03-01	California	5.0
3	2017-04-01	California	5.0
4	2017-05-01	California	4.9
...	...	...	...
3616	2022-07-01	District of Columbia	5.2
3617	2022-08-01	District of Columbia	5.1
3618	2022-09-01	District of Columbia	4.7
3619	2022-10-01	District of Columbia	4.8
3620	2022-11-01	District of Columbia	4.6

	first_day_of_month	state	unemployment_rate
48	2021-01-01	California	8.8
49	2021-02-01	California	8.6
50	2021-03-01	California	8.4
51	2021-04-01	California	8.3
52	2021-05-01	California	7.9
...	...	...	...
3605	2021-08-01	District of Columbia	6.9
3606	2021-09-01	District of Columbia	6.5
3607	2021-10-01	District of Columbia	6.3
3608	2021-11-01	District of Columbia	6.1
3609	2021-12-01	District of Columbia	6.1

	State	Unemployment
0	Alabama	3.450000
1	Alaska	6.425000
2	Arizona	4.950000
3	Arkansas	4.058333
4	California	7.366667
5	Colorado	5.408333
6	Connecticut	6.300000
7	Delaware	5.391667
8	District of Columbia	6.675000
9	Florida	4.600000
10	Georgia	3.941667
11	Hawaii	5.775000
12	Idaho	3.591667
13	Illinois	6.125000
14	Indiana	3.616667
15	Iowa	4.275000
16	Kansas	3.283333
17	Kentucky	4.708333
18	Louisiana	5.475000
19	Maine	4.633333
20	Maryland	5.783333
21	Massachusetts	5.758333
22	Michigan	5.933333
23	Minnesota	3.425000
24	Mississippi	5.625000
25	Missouri	4.375000
26	Montana	3.400000
27	Nebraska	2.516667
28	Nevada	7.250000
29	New Hampshire	3.533333
30	New Jersey	6.391667
31	New Mexico	6.808333
32	New York	6.958333
33	North Carolina	4.841667
34	North Dakota	3.683333
35	Ohio	5.166667
36	Oklahoma	3.891667
37	Oregon	5.241667
38	Pennsylvania	6.416667
39	Rhode Island	5.675000
40	South Carolina	4.016667
41	South Dakota	3.133333
42	Tennessee	4.316667
43	Texas	5.708333
44	Utah	2.716667
45	Vermont	3.450000
46	Virginia	3.925000
47	Washington	5.283333
48	West Virginia	5.075000
49	Wisconsin	3.816667
50	Wyoming	4.516667

	Unnamed: 0	Unnamed: 1	2020	2021	2022
0	United States	331449520	331511512	332031554	333287557
1	Northeast	57609156	57448898	57259257	57040406
2	Midwest	68985537	68961043	68836505	68787595
3	South	126266262	126450613	127346029	128716192
4	West	78588565	78650958	78589763	78743364
5	.Alabama	5024356	5031362	5049846	5074296
6	.Alaska	733378	732923	734182	733583
7	.Arizona	7151507	7179943	7264877	7359197
8	.Arkansas	3011555	3014195	3028122	3045637
9	.California	39538245	39501653	39142991	39029342
10	.Colorado	5773733	5784865	5811297	5839926
11	.Connecticut	3605942	3597362	3623355	3626205
12	.Delaware	989957	992114	1004807	1018396
13	.District of Columbia	689546	670868	668791	671803
14	.Florida	21538226	21589602	21828069	22244823
15	.Georgia	10711937	10729828	10788029	10912876
16	.Hawaii	1455273	1451043	1447154	1440196
17	.Idaho	1839092	1849202	1904314	1939033
18	.Illinois	12812545	12786580	12686469	12582032
19	.Indiana	6785668	6788799	6813532	6833037
20	.Iowa	3190372	3190571	3197689	3200517
21	.Kansas	2937847	2937919	2937922	2937150
22	.Kentucky	4505893	4507445	4506589	4512310
23	.Louisiana	4657749	4651664	4627098	4590241
24	.Maine	1362341	1363557	1377238	1385340
25	.Maryland	6177213	6173205	6174610	6164660
26	.Massachusetts	7029949	6995729	6989690	6981974
27	.Michigan	10077325	10069577	10037504	10034113
28	.Minnesota	5706504	5709852	5711471	5717184
29	.Mississippi	2961288	2958141	2949586	2940057
30	.Missouri	6154920	6153998	6169823	6177957
31	.Montana	1084197	1087075	1106227	1122867
32	.Nebraska	1961489	1962642	1963554	1967923
33	.Nevada	3104624	3115648	3146402	3177772
34	.New Hampshire	1377518	1378587	1387505	1395231
35	.New Jersey	9289031	9271689	9267961	9261699
36	.New Mexico	2117527	2118390	2116677	2113344
37	.New York	20201230	20108296	19857492	19677151
38	.North Carolina	10439414	10449445	10565885	10698973
39	.North Dakota	779091	779518	777934	779261
40	.Ohio	11799374	11797517	11764342	11756058
41	.Oklahoma	3959346	3964912	3991225	4019800
42	.Oregon	4237291	4244795	4256301	4240137
43	.Pennsylvania	13002689	12994440	13012059	12972008
44	.Rhode Island	1097371	1096345	1096985	1093734
45	.South Carolina	5118429	5131848	5193266	5282634
46	.South Dakota	886677	887799	896164	909824
47	.Tennessee	6910786	6925619	6968351	7051339
48	.Texas	29145428	29232474	29558864	30029572
49	.Utah	3271614	3283785	3339113	3380800
50	.Vermont	643085	642893	646972	647064
51	.Virginia	8631384	8636471	8657365	8683619
52	.Washington	7705247	7724031	7740745	7785786
53	.West Virginia	1793755	1791420	1785526	1775156
54	.Wisconsin	5893725	5896271	5880101	5892539
55	.Wyoming	576837	577605	579483	581381

	Company	Revenue	Assets	Profit	Employees	Sector	State	City	CEO_Founder	CEO_Woman	New_Entry	Profitable	CEO	Website
0	Walmart	572754.0	244860.0	13673.0	2300000	Retailing	AR	Bentonville	no	no	no	yes	C. Douglas McMillon	https://www.stock.walmart.com
1	Amazon	469822.0	420549.0	33364.0	1608000	Retailing	WA	Seattle	no	no	no	yes	Andrew R. Jassy	www.amazon.com
2	Apple	365817.0	351002.0	94680.0	154000	Technology	CA	Cupertino	no	no	no	yes	Timothy D. Cook	www.apple.com
3	CVS Health	292111.0	232999.0	7910.0	258000	Health Care	RI	Woonsocket	no	yes	no	yes	Karen Lynch	https://www.cvshealth.com
4	UnitedHealth Group	287597.0	212206.0	17285.0	350000	Health Care	MN	Minnetonka	no	no	no	yes	Andrew P. Witty	www.unitedhealthgroup.com
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
995	Vizio Holding	2124.0	935.8	-39.4	800	Industrials	CA	Irvine	yes	no	no	no	William W. Wang	https://www.vizio.com
996	1-800-Flowers.com	2122.2	1076.7	118.7	4800	Retailing	NY	Jericho	no	no	no	yes	Christopher G. McCann	https://www.1800flowers.com
997	Cowen	2112.8	8748.8	295.6	1534	Financials	NY	New York	no	no	no	yes	Jeffrey Solomon	https://www.cowen.com
998	Ashland	2111.0	6612.0	220.0	4100	Chemicals	DE	Wilmington	no	no	no	yes	Guillermo Novo	https://www.ashland.com
999	DocuSign	2107.2	2541.3	-70.0	7461	Technology	CA	San Francisco	no	no	no	no	Allan C. Thygesen	https://www.docusign.com